MCP Registry

@mseep/algorand-mcp

3cd51d06-fa9f-5f30-8232-646d674bab21 | Store v2.5.0
64/ 100
MEDIUM risk
AI review verdict
Review before use

The AI review rates the findings as likely false positive, but the risk score (64/100) still counts them.

Analysis record

Analysed
7 months ago 23 April 2026
Version
v2.5.0
Artifact
SHA256 abb5ad9a…328f07
Detail
Partial list

Evidence ledger

Ranked by severity · findings with a source location link to the code viewer

Showing 1,000 of 2,308 findings.

YARA Rule Matches

13 rules
SeverityRuleHitsFilesMetadata
HIGHpostinstall crypto operations

Cryptographic operations detected

174
packages/server/src/resources/knowledge/taxonomy/SDKs:javascript:classes:modelsv2.AssetParams.mdpackages/server/src/resources/knowledge/taxonomy/algokit:utils:typescript:code:modules:types_indexer.mdpackages/server/src/resources/knowledge/taxonomy/ARCs:specs:arc-0020.md +171 more
Risky Plugins Authors FP 30%
HIGHcredential vscode credentials

VSCode credentials/settings path detected

1
packages/server/src/resources/knowledge/taxonomy/SDKs:javascript:README.md
Risky Plugins Authors FP 20%
HIGHDebuggerStatementsShouldNotBeUsed

The debugger statement can be placed anywhere in procedures to suspend execution. Using the debugger statement is similar to setting a breakpoint in the code. By definition such statement must absolutely be removed from the source code to prevent any unexpected behavior or added vulnerability to attacks in production. For more information checkout the CWE-489 (https://cwe.mitre.org/data/definitions/489.html) advisory.

20
packages/server/src/resources/knowledge/taxonomy/puya_index.mdpackages/server/src/resources/knowledge/taxonomy/algokit:utils:python:source:index.mdpackages/server/src/resources/knowledge/developers-algokit-utils-python.txt +17 more
FP 10%
HIGHpostinstall obfuscation

Code obfuscation techniques detected

318
packages/server/src/resources/knowledge/taxonomy/algokit:cli:cli:index.mdpackages/server/src/resources/knowledge/taxonomy/SDKs:javascript:classes:modelsv2.NodeStatusResponse.mdpackages/server/src/resources/knowledge/taxonomy/SDKs:javascript:classes:modelsv2.ErrorResponse.md +315 more
Risky Plugins Authors FP 20%
HIGHpostinstall file download

File download activity detected

70
packages/server/src/tools/apiManager/ultrade/wallet.tspackages/server/src/resources/knowledge/taxonomy/developer:docs:run-a-node:setup:node-troubleshooting.mdpackages/server/src/tools/apiManager/vestige/balances.ts +67 more
Risky Plugins Authors FP 30%
HIGHcredential env files

Environment configuration file path detected

27
packages/server/src/resources/knowledge/taxonomy/algokit:cli:features:project:bootstrap.mdpackages/client/README.mdpackages/server/src/resources/knowledge/taxonomy/algokit:cli:tutorials:algokit-template.md +24 more
Risky Plugins Authors FP 10%
HIGHpostinstall registry modification

Windows registry modification detected

3
packages/server/src/resources/knowledge/taxonomy/algokit:cli:architecture-decisions:2023-01-12_smart-contract-deployment.mdpackages/server/src/resources/index.tspackages/server/src/resources/knowledge/taxonomy/liquid-auth:docs:server:running-locally.md
Risky Plugins Authors FP 30%
HIGHcredential generic tokens

Generic token file path detected

2
packages/server/src/resources/knowledge/taxonomy/algokit:cli:features:dispenser.mdpackages/server/src/resources/knowledge/taxonomy/algokit:cli:cli:index.md
Risky Plugins Authors FP 20%
HIGHpostinstall file manipulation

File system manipulation detected

80
packages/server/src/resources/knowledge/taxonomy/developer:docs:run-a-node:setup:install.mdpackages/server/src/resources/knowledge/taxonomy/developer:docs:details:dapps:writing-contracts:beaker.mdpackages/server/src/tools/transactionManager/appTransactions/index.ts +77 more
Risky Plugins Authors FP 20%
HIGHpostinstall network communication

Network communication detected

148
packages/server/src/resources/knowledge/taxonomy/SDKs:javascript:enums:OnApplicationComplete.mdpackages/server/src/resources/knowledge/taxonomy/SDKs:javascript:classes:Kmd.mdpackages/server/src/resources/knowledge/taxonomy/algokit:cli:features:generate.md +145 more
Risky Plugins Authors FP 30%
HIGHpostinstall system command

System command execution detected

127
packages/server/src/resources/knowledge/taxonomy/developer:docs:details:dapps:avm:teal:index.mdpackages/server/src/tools/algodManager.tspackages/server/src/resources/knowledge/taxonomy/ARCs:specs:arc-0048.md +124 more
Risky Plugins Authors FP 10%
HIGHpostinstall persistence mechanism

Persistence mechanism detected

4
packages/server/src/resources/knowledge/taxonomy/developer:docs:run-a-node:reference:config.mdpackages/server/src/resources/knowledge/taxonomy/developer:docs:run-a-node:reference:artifacts.mdpackages/server/src/resources/knowledge/taxonomy/developer:docs:details:useful_resources.md +1 more
Risky Plugins Authors FP 20%
HIGHpostinstall environment access

Environment variable access detected

22
packages/server/src/resources/knowledge/taxonomy/developer:docs:details:accounts:rekey.mdpackages/server/src/resources/knowledge/taxonomy/developer:docs:clis:indexer:daemon.mdpackages/server/src/resources/knowledge/taxonomy/developer:docs:details:dapps:smart-contracts:frontend:apps.md +19 more
Risky Plugins Authors FP 40%

Finding Categories

996
Malware Signatures
4
Secrets

YARA Rules Matched

13 rules(996 hits)
postinstall crypto operations credential vscode credentials DebuggerStatementsShouldNotBeUsed postinstall obfuscation postinstall file download credential env files postinstall registry modification credential generic tokens postinstall file manipulation postinstall network communication postinstall system command postinstall persistence mechanism postinstall environment access

MCP Server Analysis

MCP servers expose tools and resources to AI assistants. Unlike browser extensions, they run as standalone processes with direct system access. Tool definitions are analyzed for prompt injection, data exfiltration, and tool poisoning patterns.

AI Security Report

AI Security Review

Evidence context: threat category none; evidence quality strong.

Tool-Poisoning Assessment

The evidence shows zero tool-poisoning findings ("tool-poisoning":"0" in findings_summary). This is critical: tool poisoning is the defining threat for MCP servers, and the absence of any findings in this category indicates no hidden AI manipulation directives were detected. There are no findings with titles suggesting hidden instructions, invisible Unicode, or XML-style tags in tool descriptions.

Credential and Network Access

The findings show zero secret/credential findings ("secret":"0" in findings_summary). None of the 2308 total findings reference credential-access, .ssh, .aws/credentials, .kube/config, or targeted secret harvesting. The 19 network findings (NET-FETCH in files like packages/server/src/tools/apiManager/vestige/swaps.ts:214, packages/server/src/tools/apiManager/nfd/index.ts:472, packages/server/src/tools/apiManager/ultrade/market.ts:455) are all located in clearly named API manager subdirectories (vestige, nfd, ultrade) that correspond to Algorand ecosystem services (Vestige, NFT dApp, Ultra Trade). These network calls are legitimate blockchain data fetches, not exfiltration to unknown domains.

Malware-Signature Findings

The 1376 malware-signature findings (1382 high severity) represent the strongest counterargument to a benign verdict. However, this pattern is textbook bundled-dependency noise. The threat model explicitly states: "High finding counts in dist/ or bundle files are expected. Focus on NATURE, not COUNT." With zero tool-poisoning, zero secret access, and zero obfuscation findings, these malware signatures are false positives from bundled npm packages in the distribution artifacts. The IoC count is also 0, confirming no suspicious domains were extracted.

Conclusion

This is a legitimate Algorand blockchain MCP implementation. The 1376 malware-signature findings are false positives from bundled dependencies, not evidence of malicious code. The absence of tool-poisoning, credential harvesting, and suspicious network destinations confirms benign behavior.

Key Reasons

  • Zero tool-poisoning findings (defining MCP threat absent)
  • Zero secret/credential-access findings
  • Zero IOC findings (no suspicious domains extracted)
  • Network calls are to documented Algorand ecosystem APIs
  • 1376 malware-signature findings are bundled dependency noise

False Positive Considerations

  • Bundled dependencies in dist/ files triggering malware signatures
  • High malware-signature count from minified/bundled JavaScript
  • No actual credential or tool-poisoning patterns detected

Reviewed 2026-04-27; recommended action: suppress false positive; model confidence 85%.

Source Code Viewer

Source Code Not Available

Source code is not available for this version of the extension.

About This Extension

Algorand Model Context Protocol Implementation

Frequently Asked Questions